regexp_parser 2.8.2 → 2.9.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5309aa54a7dc49b910246ad7efd9bf1e2f6b19917c41f2c4dd389568c7a1d0c5
-  data.tar.gz: 0174ec36fcec3ca3696f7e5fbe2eeaa5e9d75b09d4e0891bd841da997101f123
+  metadata.gz: 8cc1826647cde51d6d1b5a5a58fb005efd2a38a85fa0e817616591ee2fad7862
+  data.tar.gz: 572a6203741b9970bcedc1ace243ea0b9c300ca60b71ac263036eb0f4222dd50
 SHA512:
-  metadata.gz: b52cfb89d0cb55c63844fe5f808c8472c2987746e33d71fe2ede2b9759d3f572611679050a0ae407a391c0f2ba88e9049beb579c2ead9c037b711c9a0c62b18b
-  data.tar.gz: 708e81a6463887e849ed1c560eb36abae556dc7b87c1f3fac30f74b1822a778b7d711c2fbba52ad9114db1ee5ba3a47f3898d17023de97b56799aed891e34c7f
+  metadata.gz: 3521fe6dab4be0c0db3c37f3f8d196fc754ff72937336a73ef5547a15ae4f2d366aa28e73d6e5756920d610b943ee51cb2db8e51e53ccb19c1c235a8c45da708
+  data.tar.gz: d05b7babb79c118bdc36ae168d8199ee3500b0cff33cb00ed46d51a4a88725130e931c588146a3f989dd87778b1f39684b2c8a5541c9ac8f91427fc31b1ec97a

data/Gemfile

@@ -3,13 +3,13 @@ source 'https://rubygems.org'
 gemspec
 
 group :development, :test do
-  gem 'leto', '~> 2.0'
-  gem 'rake', '~> 13.0'
-  gem 'regexp_property_values', '~> 1.4'
+  gem 'leto', '~> 2.1'
+  gem 'rake', '~> 13.1'
+  gem 'regexp_property_values', '~> 1.5'
   gem 'rspec', '~> 3.10'
   if RUBY_VERSION.to_f >= 2.7
     gem 'benchmark-ips', '~> 2.1'
     gem 'gouteur', '~> 1.1'
-    gem 'rubocop', '~> 1.7'
+    gem 'rubocop', '~> 1.59'
   end
 end

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010, 2012-2023,  Ammar Ali
+Copyright (c) 2010, 2012-2024,  Ammar Ali
 
 Permission is hereby granted, free of charge, to any person
 obtaining a copy of this software and associated documentation

data/lib/regexp_parser/expression/classes/character_set.rb

@@ -1,10 +1,7 @@
 module Regexp::Expression
   class CharacterSet < Regexp::Expression::Subexpression
     attr_accessor :closed, :negative
-
-    alias :negative? :negative
-    alias :negated?  :negative
-    alias :closed?   :closed
+    alias :closed? :closed
 
     def initialize(token, options = {})
       self.negative = false

data/lib/regexp_parser/expression/classes/posix_class.rb

@@ -1,9 +1,5 @@
 module Regexp::Expression
   class PosixClass < Regexp::Expression::Base
-    def negative?
-      type == :nonposixclass
-    end
-
     def name
       text[/\w+/]
     end

data/lib/regexp_parser/expression/classes/unicode_property.rb

@@ -1,10 +1,6 @@
 module Regexp::Expression
   module UnicodeProperty
     class Base < Regexp::Expression::Base
-      def negative?
-        type == :nonproperty
-      end
-
       def name
         text[/\A\\[pP]\{([^}]+)\}\z/, 1]
       end
@@ -109,11 +105,12 @@ module Regexp::Expression
       class Unassigned  < Codepoint::Base; end
     end
 
-    class Age     < UnicodeProperty::Base; end
-    class Derived < UnicodeProperty::Base; end
-    class Emoji   < UnicodeProperty::Base; end
-    class Script  < UnicodeProperty::Base; end
-    class Block   < UnicodeProperty::Base; end
+    class Age        < UnicodeProperty::Base; end
+    class Block      < UnicodeProperty::Base; end
+    class Derived    < UnicodeProperty::Base; end
+    class Emoji      < UnicodeProperty::Base; end
+    class Enumerated < UnicodeProperty::Base; end
+    class Script     < UnicodeProperty::Base; end
   end
 
   # alias for symmetry between token symbol and Expression class name

data/lib/regexp_parser/expression/methods/negative.rb

@@ -0,0 +1,20 @@
+module Regexp::Expression
+  module Shared
+    def negative?
+      false
+    end
+
+    # not an alias so as to respect overrides of #negative?
+    def negated?
+      negative?
+    end
+  end
+
+  Anchor::NonWordBoundary.class_eval       { def negative?; true                          end }
+  Assertion::NegativeLookahead.class_eval  { def negative?; true                          end }
+  Assertion::NegativeLookbehind.class_eval { def negative?; true                          end }
+  CharacterSet.class_eval                  { def negative?; negative                      end }
+  CharacterType::Base.class_eval           { def negative?; token.to_s.start_with?('non') end }
+  PosixClass.class_eval                    { def negative?; type == :nonposixclass        end }
+  UnicodeProperty::Base.class_eval         { def negative?; type == :nonproperty          end }
+end

data/lib/regexp_parser/expression.rb

@@ -28,6 +28,7 @@ require 'regexp_parser/expression/methods/construct'
 require 'regexp_parser/expression/methods/human_name'
 require 'regexp_parser/expression/methods/match'
 require 'regexp_parser/expression/methods/match_length'
+require 'regexp_parser/expression/methods/negative'
 require 'regexp_parser/expression/methods/options'
 require 'regexp_parser/expression/methods/parts'
 require 'regexp_parser/expression/methods/printing'

data/lib/regexp_parser/parser.rb

@@ -467,6 +467,7 @@ class Regexp::Parser
     when *UPTokens::Age;          node << UP::Age.new(token, active_opts)
     when *UPTokens::Derived;      node << UP::Derived.new(token, active_opts)
     when *UPTokens::Emoji;        node << UP::Emoji.new(token, active_opts)
+    when *UPTokens::Enumerated;   node << UP::Enumerated.new(token, active_opts)
     when *UPTokens::Script;       node << UP::Script.new(token, active_opts)
     when *UPTokens::UnicodeBlock; node << UP::Block.new(token, active_opts)
 

data/lib/regexp_parser/scanner/properties/long.csv

@@ -8,6 +8,7 @@ age=12.1,age=12.1
 age=13.0,age=13.0
 age=14.0,age=14.0
 age=15.0,age=15.0
+age=15.1,age=15.1
 age=2.0,age=2.0
 age=2.1,age=2.1
 age=3.0,age=3.0
@@ -108,6 +109,19 @@ gothic,gothic
 grantha,grantha
 graph,graph
 graphemebase,grapheme_base
+graphemeclusterbreak=control,grapheme_cluster_break=control
+graphemeclusterbreak=cr,grapheme_cluster_break=cr
+graphemeclusterbreak=extend,grapheme_cluster_break=extend
+graphemeclusterbreak=l,grapheme_cluster_break=l
+graphemeclusterbreak=lf,grapheme_cluster_break=lf
+graphemeclusterbreak=lv,grapheme_cluster_break=lv
+graphemeclusterbreak=lvt,grapheme_cluster_break=lvt
+graphemeclusterbreak=prepend,grapheme_cluster_break=prepend
+graphemeclusterbreak=regionalindicator,grapheme_cluster_break=regional_indicator
+graphemeclusterbreak=spacingmark,grapheme_cluster_break=spacingmark
+graphemeclusterbreak=t,grapheme_cluster_break=t
+graphemeclusterbreak=v,grapheme_cluster_break=v
+graphemeclusterbreak=zwj,grapheme_cluster_break=zwj
 graphemeextend,grapheme_extend
 graphemelink,grapheme_link
 greek,greek
@@ -123,11 +137,14 @@ hebrew,hebrew
 hexdigit,hex_digit
 hiragana,hiragana
 hyphen,hyphen
+idcompatmathcontinue,id_compat_math_continue
+idcompatmathstart,id_compat_math_start
 idcontinue,id_continue
 ideographic,ideographic
 idsbinaryoperator,ids_binary_operator
 idstart,id_start
 idstrinaryoperator,ids_trinary_operator
+idsunaryoperator,ids_unary_operator
 imperialaramaic,imperial_aramaic
 inadlam,in_adlam
 inaegeannumbers,in_aegean_numbers
@@ -190,6 +207,7 @@ incjkunifiedideographsextensione,in_cjk_unified_ideographs_extension_e
 incjkunifiedideographsextensionf,in_cjk_unified_ideographs_extension_f
 incjkunifiedideographsextensiong,in_cjk_unified_ideographs_extension_g
 incjkunifiedideographsextensionh,in_cjk_unified_ideographs_extension_h
+incjkunifiedideographsextensioni,in_cjk_unified_ideographs_extension_i
 incombiningdiacriticalmarks,in_combining_diacritical_marks
 incombiningdiacriticalmarksextended,in_combining_diacritical_marks_extended
 incombiningdiacriticalmarksforsymbols,in_combining_diacritical_marks_for_symbols

data/lib/regexp_parser/scanner/properties/short.csv

@@ -86,6 +86,7 @@ ideo,ideographic
 ids,id_start
 idsb,ids_binary_operator
 idst,ids_trinary_operator
+idsu,ids_unary_operator
 ital,old_italic
 java,javanese
 joinc,join_control

data/lib/regexp_parser/scanner/scanner.rl

@@ -364,6 +364,7 @@
   conditional_expression := |*
     group_lookup . ')' {
       text = copy(data, ts, te-1)
+      text =~ /[^0]/ or raise ValidationError.for(:backref, 'condition', 'invalid ref ID')
       emit(:conditional, :condition, text)
       emit(:conditional, :condition_close, ')')
     };
@@ -541,13 +542,13 @@
       case text = copy(data, ts, te)
       when /^\\k(.)[^0-9\-][^+\-]*['>]$/
         emit(:backref, $1 == '<' ? :name_ref_ab : :name_ref_sq, text)
-      when /^\\k(.)[1-9]\d*['>]$/
+      when /^\\k(.)0*[1-9]\d*['>]$/
         emit(:backref, $1 == '<' ? :number_ref_ab : :number_ref_sq, text)
-      when /^\\k(.)-[1-9]\d*['>]$/
+      when /^\\k(.)-0*[1-9]\d*['>]$/
         emit(:backref, $1 == '<' ? :number_rel_ref_ab : :number_rel_ref_sq, text)
       when /^\\k(.)[^0-9\-].*[+\-]\d+['>]$/
         emit(:backref, $1 == '<' ? :name_recursion_ref_ab : :name_recursion_ref_sq, text)
-      when /^\\k(.)-?[1-9]\d*[+\-]\d+['>]$/
+      when /^\\k(.)-?0*[1-9]\d*[+\-]\d+['>]$/
         emit(:backref, $1 == '<' ? :number_recursion_ref_ab : :number_recursion_ref_sq, text)
       else
         raise ValidationError.for(:backref, 'backreference', 'invalid ref ID')
@@ -560,9 +561,9 @@
       case text = copy(data, ts, te)
       when /^\\g(.)[^0-9+\-].*['>]$/
         emit(:backref, $1 == '<' ? :name_call_ab : :name_call_sq, text)
-      when /^\\g(.)\d+['>]$/
+      when /^\\g(.)(?:0|0*[1-9]\d*)['>]$/
         emit(:backref, $1 == '<' ? :number_call_ab : :number_call_sq, text)
-      when /^\\g(.)[+-]\d+/
+      when /^\\g(.)[+-]0*[1-9]\d*/
         emit(:backref, $1 == '<' ? :number_rel_call_ab : :number_rel_call_sq, text)
       else
         raise ValidationError.for(:backref, 'subexpression call', 'invalid ref ID')

data/lib/regexp_parser/scanner.rb

@@ -1570,6 +1570,7 @@ end
 te = p+1
  begin
       text = copy(data, ts, te-1)
+      text =~ /[^0]/ or raise ValidationError.for(:backref, 'condition', 'invalid ref ID')
       emit(:conditional, :condition, text)
       emit(:conditional, :condition_close, ')')
      end
@@ -1750,13 +1751,13 @@ te = p+1
       case text = copy(data, ts, te)
       when /^\\k(.)[^0-9\-][^+\-]*['>]$/
         emit(:backref, $1 == '<' ? :name_ref_ab : :name_ref_sq, text)
-      when /^\\k(.)[1-9]\d*['>]$/
+      when /^\\k(.)0*[1-9]\d*['>]$/
         emit(:backref, $1 == '<' ? :number_ref_ab : :number_ref_sq, text)
-      when /^\\k(.)-[1-9]\d*['>]$/
+      when /^\\k(.)-0*[1-9]\d*['>]$/
         emit(:backref, $1 == '<' ? :number_rel_ref_ab : :number_rel_ref_sq, text)
       when /^\\k(.)[^0-9\-].*[+\-]\d+['>]$/
         emit(:backref, $1 == '<' ? :name_recursion_ref_ab : :name_recursion_ref_sq, text)
-      when /^\\k(.)-?[1-9]\d*[+\-]\d+['>]$/
+      when /^\\k(.)-?0*[1-9]\d*[+\-]\d+['>]$/
         emit(:backref, $1 == '<' ? :number_recursion_ref_ab : :number_recursion_ref_sq, text)
       else
         raise ValidationError.for(:backref, 'backreference', 'invalid ref ID')
@@ -1770,9 +1771,9 @@ te = p+1
       case text = copy(data, ts, te)
       when /^\\g(.)[^0-9+\-].*['>]$/
         emit(:backref, $1 == '<' ? :name_call_ab : :name_call_sq, text)
-      when /^\\g(.)\d+['>]$/
+      when /^\\g(.)(?:0|0*[1-9]\d*)['>]$/
         emit(:backref, $1 == '<' ? :number_call_ab : :number_call_sq, text)
-      when /^\\g(.)[+-]\d+/
+      when /^\\g(.)[+-]0*[1-9]\d*/
         emit(:backref, $1 == '<' ? :number_rel_call_ab : :number_rel_call_sq, text)
       else
         raise ValidationError.for(:backref, 'subexpression call', 'invalid ref ID')

data/lib/regexp_parser/syntax/token/unicode_property.rb

@@ -703,6 +703,24 @@ module Regexp::Syntax
         extended_pictographic
       ]
 
+      Enumerated_V2_4_0 = %i[
+        grapheme_cluster_break=control
+        grapheme_cluster_break=cr
+        grapheme_cluster_break=extend
+        grapheme_cluster_break=l
+        grapheme_cluster_break=lf
+        grapheme_cluster_break=lv
+        grapheme_cluster_break=lvt
+        grapheme_cluster_break=prepend
+        grapheme_cluster_break=regional_indicator
+        grapheme_cluster_break=spacingmark
+        grapheme_cluster_break=t
+        grapheme_cluster_break=v
+        grapheme_cluster_break=zwj
+      ]
+
+      Enumerated = all[:Enumerated_V]
+
       Emoji = all[:Emoji_V]
 
       V1_9_0 = Category::All + POSIX + all[:V1_9_0]

data/lib/regexp_parser/version.rb

@@ -1,5 +1,5 @@
 class Regexp
   class Parser
-    VERSION = '2.8.2'
+    VERSION = '2.9.0'
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: regexp_parser
 version: !ruby/object:Gem::Version
-  version: 2.8.2
+  version: 2.9.0
 platform: ruby
 authors:
 - Ammar Ali
@@ -9,7 +9,7 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-10-10 00:00:00.000000000 Z
+date: 2024-01-07 00:00:00.000000000 Z
 dependencies: []
 description: A library for tokenizing, lexing, and parsing Ruby regular expressions.
 email:
@@ -46,6 +46,7 @@ files:
 - lib/regexp_parser/expression/methods/human_name.rb
 - lib/regexp_parser/expression/methods/match.rb
 - lib/regexp_parser/expression/methods/match_length.rb
+- lib/regexp_parser/expression/methods/negative.rb
 - lib/regexp_parser/expression/methods/options.rb
 - lib/regexp_parser/expression/methods/parts.rb
 - lib/regexp_parser/expression/methods/printing.rb